© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217990
    Prev
    Next
    INDEX
    Explanations

    recordings, ready, stains, Lobby

    np_acts-logits-general · gemini-2.5-flash-lite

    menu offerings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     خواهند
    0.49
     چی
    0.48
    لوں
    0.47
    ()!=
    0.46
     olacaktır
    0.45
    یرے
    0.43
     bosonic
    0.43
    ادو
    0.42
    ulated
    0.42
    یدم
    0.42
    POSITIVE LOGITS
    一件
    0.48
    人心
    0.48
    这个
    0.48
    اه
    0.45
    容
    0.45
     Punt
    0.45
    奢
    0.44
    حظ
    0.44
    顽
    0.43
     Олександр
    0.42
    Activations Density 0.000%

    No Known Activations